Engineering Commons^™

Real-Time Sound Source Separation For Music Applications, Dan Barry

Doctoral

Sound source separation refers to the task of extracting individual sound sources from some number of mixtures of those sound sources. In this thesis, a novel sound source separation algorithm for musical applications is presented. It leverages the fact that the vast majority of commercially recorded music since the 1950s has been mixed down for two channel reproduction, more commonly known as stereo. The algorithm presented in Chapter 3 in this thesis requires no prior knowledge or learning and performs the task of separation based purely on azimuth discrimination within the stereo field. The algorithm exploits the use of the …